How does solr choose labels when using STC algorithm

Question

I am currently trying to use Solr to do clustering. I am using the STC algorithm. However, I do not know how the labels of clusters are generated. I know that the labels of the nodes in the suffix tree are used, but in what way? What suffix(terms) will be chosen? Thank you.

Answer 1

STC is the implementation of Oren Zamir's Suffix Tree Clustering algorithm. For an in-depth description of the algorithm, take a look at Zamir's PhD dissertation.